From owner-freebsd-current@FreeBSD.ORG Sun Jul 25 00:22:17 2004 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 416C316A4CF for ; Sun, 25 Jul 2004 00:22:17 +0000 (GMT) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id D326843D3F for ; Sun, 25 Jul 2004 00:22:16 +0000 (GMT) (envelope-from scottl@freebsd.org) Received: from [192.168.0.12] (g4.samsco.home [192.168.0.12]) (authenticated bits=0) by pooker.samsco.org (8.12.11/8.12.10) with ESMTP id i6P0SkDp076728; Sat, 24 Jul 2004 18:28:46 -0600 (MDT) (envelope-from scottl@freebsd.org) Message-ID: <4102FCF2.60708@freebsd.org> Date: Sat, 24 Jul 2004 18:21:06 -0600 From: Scott Long User-Agent: Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.7) Gecko/20040514 X-Accept-Language: en-us, en MIME-Version: 1.0 To: conrads@cox.net References: In-Reply-To: Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Status: No, hits=0.0 required=3.8 tests=none autolearn=no version=2.63 X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on pooker.samsco.org cc: freebsd-current@freebsd.org Subject: Re: [amd64] Instability worse than ever X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 25 Jul 2004 00:22:17 -0000 Conrad J. Sabatier wrote: > For the last couple of days, my amd64 box has taken to spontaneously > rebooting. No panic, no coredump, nothing in logs, just reboots. > > These always seem to occur just as I'm clicking on something under > GNOME. > > Very mysterious! > Do you have INVARIANTS turned on? If you do, would you be able to hook up a serial console and see what the kernel is saying? Also, a quick hack that might help you is to take either sched_4bsd.c or sched_ule.c (depending on which you are using) and comment out the call to maybe_preempt(td) in sched_add() like so: + if 0 if (maybe_preempt(td)) return; + endif I think I understand most of the underlying problem with much of the recent (and not so recent) instability, but I haven't come up with an acceptable solution yet. If anyone is interested in helping (code, not test), please let me know. Scott